No description available.

It is now widely accepted that human behaviour accounts for a large portion of total global emissions, and thus influences climate change to a large extent. Changing human behaviour when it comes to mode of transportation is one component which could make a difference in the long term. In order to achieve behavioural change, we investigate the use of a persuasive multiplayer game. Transportation mode recognition is used within the game to provide bonuses and penalties to users based on their daily choices regarding transportation. To easily identify modes of transportation, an approach to transport recognition based on accelerometer and gyroscope data is analysed and extended. Preliminary results from the machine learning tests show that the classification true-positive rate for recognizing 10 different classes can reach up to 95% when using a history set (66% without). Preliminary results from testers of the game indicate that using games may be successful in causing positive change in user behaviour. / <p>Del av Erasmus Mundus PERCCOM. Redovisning skedde på anordnad summer school av partner-universitet där hela konsortiet närvarade.</p>

A wide range of contemporary technologies leveraging ubiquitous mobile phones have addressed the challenge of transportation mode recognition, which involves identifying how users move about, such as walking, cycling, driving a car, or taking a bus. This problem has found applications in various areas, including smart city transportation, carbon footprint calculation, and context-aware mobile assistants. Previous research has primarily focused on recognizing mobility modes using GPS and motion sensor data from smartphones. However, these approaches often necessitate the installation of specialized mobile applications on users’ devices to collect sensor data, resulting in power inefficiency and privacy concerns. In this study, we tackle these issues by presenting a user-independent system capable of distinguishing four forms of locomotion—walking, bus, car, and train—solely based on mobile data (4G) from smartphones. Our system was developed using data collected in three diverse locations (Mekkah, Jeddah, KAUST) in the Kingdom of Saudi Arabia. The underlying concept is to correlate phone speed with features extracted from Channel State Information (CSI), which includes information about Physical Cell ID, received signal strength, and other relevant data. The feature extraction process involves utilizing sliding windows over both the time and frequency domains. By employing statistical classification and boosting techniques, we achieved remarkable F-scores of 85%, 95%, 88%, and 70% for the car, bus, walking, and train modes, respectively. Moreover, we conducted an analysis of the handover rate in a one-tier network and compared the analytical results with real data. This investigation provided novel insights into the influence of transportation modes on handover rate, revealing the correlation between different modes of mobility and network connectivity. This work sets the stage for the development of more efficient and privacy-friendly solutions in transportation mode recognition and network optimization.

The fast development in telecommunication is producing a huge amount of data related to how people move and behave over time. Nowadays, travel data are mainly collected through Global Positioning Systems (GPS) and can be used to identify human mobility patterns and travel behaviors. Transport mode detection (TMD) aims to identify the means of transport used by an individual and is a field that has become more popular in recent years as it can be beneficial for various applications. However, developing travel models requires different types of information that can be extracted from raw travel data. Although many useful features like speed, acceleration and bearing rate can be extracted from raw GPS data, detecting transport modes requires further processing. Some previous studies have successfully applied machine learning algorithms for detecting the transport mode. Despite achieving high performance in their models, many of these studies have used rather small datasets generated from a limited number of users or identified a small number of different transport modes. Furthermore, in most of these studies more complex methodologies have been applied, where extra information like GIS layers or road and railway networks were required. The purpose of this study is to propose a simple supervised learning model to identify five common transport modes on large datasets by only using raw GPS data. In total, six commonly used supervised learning algorithms are tested on seven selected features (extracted from raw GPS data). The Random Forest (RF) algorithm proves to perform better in detecting five transport modes from the dataset utilized in this study, with an overall accuracy of 82.7%.

Le travail développé dans ce manuscrit porte sur la synchronisation des systèmes chaotiques. Il est articulé autour de deux axes principaux: la synthèse d'observateur et la détection de mode. Dans un premier temps, quelques rappels sur le chaos et les principales architectures de systèmes de chiffrement chaotiques sont effectués. Ensuite, nous montrons comment les systèmes chaotiques à non linéarité polynomiale ou affines à commutation peuvent se réécrire sous forme LPV polytopique. Une revue des principaux résultats sur la synthèse d'observateurs LPV polytopiques reposant sur l'utilisation des LMI est faite. Une extension des résultats aux observateurs polytopiques à entrées inconnues, à la fois dans le cas déterministe, bruité ou incertain est proposée. Ces observateurs assurent la synchronisation du chaos et donc le déchiffrement dans les systèmes de chiffrement "modulation paramétrique", "commutation chaotique", "transmission à deux canaux" et "chiffrement par inclusion". Pour les systèmes affines à commutation utilisés en tant que générateur du chaos, le cas où l'état discret n'est pas accessible est considéré. Une présentation unifiée des méthodes fondées sur les espaces de parité, proposées dans la littérature pour les systèmes linéaires et affines à commutation à temps discret, est réalisée. Le problème de discernabilité fait l'objet d'une étude approfondie. Une approche pour estimer les retards variables des systèmes affines et affines à commutation à temps discret, formulée en termes de détection de mode, est proposée en tant que solution à l'estimation de retard pour le chiffrement par injection de retard / The work developed in this manuscript addresses the synchronization of chaotic systems. It is organized around two main axes: the observer synthesis and the mode detection. In a first step, we recall the main architectures of chaotic encryption systems and show how chaotic systems with polynomial nonlinearities or switched affine dynamics can be rewritten in a polytopic LPV form. A review of the main LMI based results for polytopic LPV observers synthesis is made. An extension to polytopic unknown input observers, both in the deterministic case and noisy or uncertain case, is proposed. These observers ensure chaos synchronization and information recovering in the framework of the following encryption systems: "parametric modulation", "chaotic switching", "two channels transmission" and "inclusion encryption". For affine switched systems used as a generator of chaos, the case where the discrete state is not available is considered. A unified presentation of mode detection methods based on parity spaces proposed in the literature for linear and affine switched discrete time systems is proposed. The problem of discernibility is the subject of a complete study. An approach to estimate time varying delays for affine switched discrete time systems, formulated in terms of mode detection, is proposed as a solution for delay injection encryption

Understanding travel behavior and identifying the mode of transportation are essential for adequate urban devising and transportation planning. Global positioning systems (GPS) tracking data is mainly used to find human mobility patterns in cities. Some travel information, such as most visited location, temporal changes, and the trip speed, can be easily extracted from GPS raw tracking data. GPS trajectories can be used as a method to indicate the mobility modes of commuters. Most previous studies have applied traditional machine learning algorithms and manually computed data features, making the model error-prone. Thus, there is a demand for developing a new model to resolve these methods' weaknesses. The primary purpose of this study is to propose a semi-supervised model to identify transportation mode by using a contemporary machine learning algorithm and GPS tracking data. The model can accept GPS trajectory with adjustable length and extracts their latent information with LSTM Autoencoder. This study adopts a deep neural network architecture with three hidden layers to map the latent information to detect transportation mode. Moreover, different case studies are performed to evaluate the proposed model's efficiency. The model results in an accuracy of 93.6%, which significantly outperforms similar studies.

Ett sätt att informera smartphone-användare om deras klimatpåverkan är genom att automatiskt identifiera vilket transportmedel användaren nyttjat och använda informationen för att uppskatta användarens utsläpp av växthusgaser. Målet med det här projektet var att sammanställa en översikt av befintliga lösningar och metoder för att detektera smartphone-användares transportmedel och utvärdera hur ett system presterar då testdata är samlad i ett annat geografiskt område än datan som använts för att träna systemet. Utvärdering av systemet skedde via kvantitativa metoder där sensordata samlades in och användes för att testa systemet. Sensordata samlades vid gång, stilla, tåg, buss och bil. Resultatet är ett system som med varierande sannolikhet kan avgöra transportmedel i Sverige. Systemets totala precision var 29 procentenheter lägre då data som samlats i Sverige användes i testerna jämfört med data insamlad i samma geografiska område som träningsdatan. Slutsatsen är att det kan vara problematiskt att applicera en lösning i ett annat geografiskt område än lösningen utvecklats för. Genom testerna framkom att fordonstransport verkar särskilt känsligt vid byte av geografisk kontext. / A way to inform smartphone users about their climate impact is by automatically identifying their means of transport and use the information to estimate the user's emissions of greenhouse gases. The aim of this project was to create an overview of existing solutions and methods for detecting smartphone users' means of transport and evaluating how a system performs when test data is collected in a different geographical area than the data used to train the system. Evaluation of the system was done via quantitative methods where sensor data was collected and used to test the system. Sensor data was collected by walking, still, train, bus and car. The result is a system that, with varying probability, can determine the means of transport in Sweden. The system's total accuracy was 29 percentage points lower when data collected in Sweden was used in the tests compared to data collected in the same geographical area as the training data. The conclusion is that it can be problematic to apply a solution in a different geographical area than where the solution was developed for. The tests showed that vehicle detection seems particularly sensitive to changing geographical context.

Identification of travelers' transportation modes is a fundamental step for various problems that arise in the domain of transportation such as travel demand analysis, transport planning, and traffic management. This thesis aims to identify travelers' transportation modes purely based on their GPS trajectories. First, a segmentation process is developed to partition a user's trip into GPS segments with only one transportation mode. A majority of studies have proposed mode inference models based on hand-crafted features, which might be vulnerable to traffic and environmental conditions. Furthermore, the classification task in almost all models have been performed in a supervised fashion while a large amount of unlabeled GPS trajectories has remained unused. Accordingly, a deep SEmi-Supervised Convolutional Autoencoder (SECA) architecture is proposed to not only automatically extract relevant features from GPS segments but also exploit useful information in unlabeled data. The SECA integrates a convolutional-deconvolutional autoencoder and a convolutional neural network into a unified framework to concurrently perform supervised and unsupervised learning. The two components are simultaneously trained using both labeled and unlabeled GPS segments, which have already been converted into an efficient representation for the convolutional operation. An optimum schedule for varying the balancing parameters between reconstruction and classification errors are also implemented. The performance of the proposed SECA model, trip segmentation, the method for converting a raw trajectory into a new representation, the hyperparameter schedule, and the model configuration are evaluated by comparing to several baselines and alternatives for various amounts of labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed model over the state-of-the-art semi-supervised and supervised methods with respect to metrics such as accuracy and F-measure. / Master of Science / Identifying users' transportation modes (e.g., bike, bus, train, and car) is a key step towards many transportation related problems including (but not limited to) transport planning, transit demand analysis, auto ownership, and transportation emissions analysis. Traditionally, the information for analyzing travelers' behavior for choosing transport mode(s) was obtained through travel surveys. High cost, low-response rate, time-consuming manual data collection, and misreporting are the main demerits of the survey-based approaches. With the rapid growth of ubiquitous GPS-enabled devices (e.g., smartphones), a constant stream of users' trajectory data can be recorded. A user's GPS trajectory is a sequence of GPS points, recorded by means of a GPS-enabled device, in which a GPS point contains the information of the device geographic location at a particular moment. In this research, users' GPS trajectories, rather than traditional resources, are harnessed to predict their transportation mode by means of statistical models. With respect to the statistical models, a wide range of studies have developed travel mode detection models using on hand-designed attributes and classical learning techniques. Nonetheless, hand-crafted features cause some main shortcomings including vulnerability to traffic uncertainties and biased engineering justification in generating effective features. A potential solution to address these issues is by leveraging deep learning frameworks that are capable of capturing abstract features from the raw input in an automated fashion. Thus, in this thesis, deep learning architectures are exploited in order to identify transport modes based on only raw GPS tracks. It is worth noting that a significant portion of trajectories in GPS data might not be annotated by a transport mode and the acquisition of labeled data is a more expensive and labor-intensive task in comparison with collecting unlabeled data. Thus, utilizing the unlabeled GPS trajectory (i.e., the GPS trajectories that have not been annotated by a transport mode) is a cost-effective approach for improving the prediction quality of the travel mode detection model. Therefore, the unlabeled GPS data are also leveraged by developing a novel deep-learning architecture that is capable of extracting information from both labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed models over the state-of-the-art methods in literature with respect to several performance metrics.

GPS tracking data are widely used to understand human travel behavior and to evaluate the impact of travel. A major advantage with the usage of GPS tracking devices for collecting data is that it enables the researcher to collect large amounts of highly accurate and detailed human mobility data. However, unlabeled GPS tracking data does not easily lend itself to detecting transportation mode and this has given rise to a range of methods and algorithms for this purpose. The algorithms used vary in design and functionality, from defining specific rules to advanced machine learning algorithms. There is however no previous comprehensive review of these algorithms and this thesis aims to identify their essential features and methods and to develop and demonstrate a method for the detection of transport mode in GPS tracking data. To do this, it is necessary to have a detailed description of the particular journey undertaken by an individual. Therefore, as part of the investigation, a microdata analytic approach is applied to the problem areas, including the stages of data collection, data processing, analyzing the data, and decision making. In order to fill the research gap, Paper I consists of a systematic literature review of the methods and essential features used for detecting the transport mode in unlabeled GPS tracking data. Selected empirical studies were categorized into rule-based methods, statistical methods, and machine learning methods. The evaluation shows that machine learning algorithms are the most common. In the evaluation, I compared the methods previously used, extracted features, types of dataset, and model accuracy of transport mode detection. The results show that there is no standard method used in transport mode detection. In the light of these results, I propose in Paper II a stepwise methodology to detect five transport modes taking advantage of the unlabeled GPS data by first using an unsupervised algorithm to detect the five transport modes. A GIS multi-criteria process was applied to label part of the dataset. The performance of the five supervised algorithms was evaluated by applying them to different portions of the labeled dataset. The results show that stepwise methodology can achieve high accuracy in detecting the transport mode by labeling only 10% of the data from the entire dataset.  For the future, one interesting area to explore would be the application of the stepwise methodology to a balanced and larger dataset. A semi-supervised deep-learning approach is suggested for development in transport mode detection, since this method can detect transport modes with only small amounts of labeled data. Thus, the stepwise methodology can be improved upon for further studies.

The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. A cost-effective approach for improving and optimizing transportation-related problems is to unlock hidden knowledge in ever-increasing spatiotemporal and crowdsourced information collected from various sources such as mobile phone sensors (e.g., GPS sensors) and social media networks (e.g., Twitter). Data mining and machine learning techniques are the major tools for analyzing the collected data and extracting useful knowledge on traffic conditions and mobility behaviors. Deep learning is an advanced branch of machine learning that has enjoyed a lot of success in computer vision and natural language processing fields in recent years. However, deep learning techniques have been applied to only a small number of transportation applications such as traffic flow and speed prediction. Accordingly, my main objective in this dissertation is to develop state-of-the-art deep learning architectures for resolving the transport-related applications that have not been treated by deep learning architectures in much detail, including (1) travel mode detection, (2) vehicle classification, and (3) traffic information system. To this end, an efficient representation for spatiotemporal and crowdsourced data (e.g., GPS trajectories) is also required to be designed in such a way that not only be adaptable with deep learning architectures but also contains efficient information for solving the task-at-hand. Furthermore, since the good performance of a deep learning algorithm is primarily contingent on access to a large volume of training samples, efficient data collection and labeling strategies are developed for different data types and applications. Finally, the performance of the proposed representations and models are evaluated by comparing to several state-of-the-art techniques in literature. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application. / PHD / The rapid growth of population and the permanent increase in the number of vehicles engender several issues in transportation systems, which in turn call for an intelligent and cost-effective approach to resolve the problems in an efficient manner. Furthermore, the recent advances in positioning tools (e.g., GPS sensors) and ever-popularity of social media networks have enabled generation of massive spatiotemporal and crowdsourced data. This dissertation aims to leverage the advances in artificial intelligence so as to unlock the rick knowledge in the recorded data and in turn, optimizing the transportation systems in a cost-effective way. In particular, this dissertation seeks for proposing end-to-end frameworks based on deep learning models, as an advanced branch of artificial intelligence, as well as spatiotemporal and crowdsourced datasets (e.g., GPS trajectory and social media) for improving three transportation problems. (1) Travel Mode Detection, which is defined as identifying users’ transportation mode(s) (e.g., walk, bike, bus, car, and train) when traveling around the traffic network. (2) Vehicle Classification, which is defined as identifying the vehicle’s type (e.g., passenger car and truck) while moving in a traffic network. (3) traffic information system based on social media networks, which is defined as detecting traffic events (e.g., crash) and capturing traffic information (e.g., traffic congestion) on a real-time basis from users’ tweets. The experimental results clearly and consistently demonstrate the superiority of the proposed deep-learning based framework for each application.